© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14937
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and political actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.11
    0.3%
    555
    +0.11
    0.3%
    1108
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.11
    0.05
    1507
    +0.11
    0.03
    1512
    +0.11
    0.03
    Negative Logits
     emphat
    -1.13
     wherea
    -1.05
     psg
    -1.00
     fuf
    -1.00
     inconce
    -0.99
     inev
    -0.99
     fte
    -0.98
     increa
    -0.98
     stockholm
    -0.98
     uniqu
    -0.98
    POSITIVE LOGITS
    Nhưng
    0.56
     bawat
    0.55
    Obrázky
    0.54
     panahon
    0.49
    RITION
    0.48
     ibang
    0.47
     digress
    0.47
    makeText
    0.47
     buhay
    0.47
    fml
    0.46
    Activations Density 0.291%

    No Known Activations